Continual Learning for Acoustic Event Classification

Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device acoustic event classification given the restrictions on computation resources (e.g., model size, running memory). To alleviate such an issue, we propose two novel diversity-aware incremental learning method for Spoken Keyword Spotting and Environmental Sound Classification. Our method selects the historical data for the training by measuring the per-sample classification uncertainty. For the Spoken Keyword Spotting application, the proposed RK approach introduces a diversity-aware sampler to select a diverse set from historical and incoming keywords by calculating classification uncertainty. As a result, the RK approach can incrementally learn new tasks without forgetting prior knowledge. Besides, the RK approach also proposes data augmentation and knowledge distillation loss function for efficient memory management on the edge device. For the Environmental Sound Classification application, we measure the uncertainty by observing how the classification probability of data fluctuates against the parallel perturbations added to the classifier embedding. In this way, the computation cost can be significantly reduced compared with adding perturbation to the raw data. Experimental results show that the proposed RK approach achieves 4.2% absolute improvement in terms of average accuracy over the best baseline on Google Speech Command dataset with less required memory. Experimental results on the DCASE 2019 Task 1 and ESC-50 dataset show that our proposed method outperforms baseline continual learning methods on classification accuracy and computational efficiency, indicating our method can efficiently and incrementally learn new classes without the catastrophic forgetting problem for on-device environmental sound classification

VABench: A Comprehensive Benchmark for Audio-Video Generation

Recent advances in video generation have been remarkable, enabling models to produce visually compelling videos with synchronized audio. While existing video generation benchmarks provide comprehensive metrics for visual quality, they lack convincing evaluations for audio-video generation, especially for models aiming to generate synchronized audio-video outputs. To address this gap, we introduce VABench, a comprehensive and multi-dimensional benchmark framework designed to systematically evaluate the capabilities of synchronous audio-video generation. VABench encompasses three primary task types: text-to-audio-video (T2AV), image-to-audio-video (I2AV), and stereo audio-video generation. It further establishes two major evaluation modules covering 15 dimensions. These dimensions specifically assess pairwise similarities (text-video, text-audio, video-audio), audio-video synchronization, lip-speech consistency, and carefully curated audio and video question-answering (QA) pairs, among others. Furthermore, VABench covers seven major content categories: animals, human sounds, music, environmental sounds, synchronous physical sounds, complex scenes, and virtual worlds. We provide a systematic analysis and visualization of the evaluation results, aiming to establish a new standard for assessing video generation models with synchronous audio capabilities and to promote the comprehensive advancement of the field.

NeuroSketch: An Effective Framework for Neural Decoding via Systematic Architectural Optimization

Neural decoding, a critical component of Brain-Computer Interface (BCI), has recently attracted increasing research interest. Previous research has focused on leveraging signal processing and deep learning methods to enhance neural decoding performance. However, the in-depth exploration of model architectures remains underexplored, despite its proven effectiveness in other tasks such as energy forecasting and image classification. In this study, we propose NeuroSketch, an effective framework for neural decoding via systematic architecture optimization. Starting with the basic architecture study, we find that CNN-2D outperforms other architectures in neural decoding tasks and explore its effectiveness from temporal and spatial perspectives. Building on this, we optimize the architecture from macro- to micro-level, achieving improvements in performance at each step. The exploration process and model validations take over 5,000 experiments spanning three distinct modalities (visual, auditory, and speech), three types of brain signals (EEG, SEEG, and ECoG), and eight diverse decoding tasks. Experimental results indicate that NeuroSketch achieves state-of-the-art (SOTA) performance across all evaluated datasets, positioning it as a powerful tool for neural decoding. Our code and scripts are available at https://github.com/Galaxy-Dawn/NeuroSketch.

UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking

Generating lifelike conversational avatars requires modeling not just isolated speakers, but the dynamic, reciprocal interaction of speaking and listening. However, modeling the listener is exceptionally challenging: direct audio-driven training fails, producing stiff, static listening motions. This failure stems from a fundamental imbalance: the speaker's motion is strongly driven by speech audio, while the listener's motion primarily follows an internal motion prior and is only loosely guided by external speech. This challenge has led most methods to focus on speak-only generation. The only prior attempt at joint generation relies on extra speaker's motion to produce the listener. This design is not end-to-end, thereby hindering the real-time applicability. To address this limitation, we present UniLS, the first end-to-end framework for generating unified speak-listen expressions, driven by only dual-track audio. Our method introduces a novel two-stage training paradigm. Stage 1 first learns the internal motion prior by training an audio-free autoregressive generator, capturing the spontaneous dynamics of natural facial motion. Stage 2 then introduces the dual-track audio, fine-tuning the generator to modulate the learned motion prior based on external speech cues. Extensive evaluations show UniLS achieves state-of-the-art speaking accuracy. More importantly, it delivers up to 44.1\% improvement in listening metrics, generating significantly more diverse and natural listening expressions. This effectively mitigates the stiffness problem and provides a practical, high-fidelity audio-driven solution for interactive digital humans.

VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio

General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting. Unlike supervised classification benchmarks that measure adaptability via parameter updates, we introduce VocSim, a training-free benchmark probing the intrinsic geometric alignment of frozen embeddings. VocSim aggregates 125k single-source clips from 19 corpora spanning human speech, animal vocalizations, and environmental sounds. By restricting to single-source audio, we isolate content representation from the confound of source separation. We evaluate embeddings using Precision@k for local purity and the Global Separation Rate (GSR) for point-wise class separation. To calibrate GSR, we report lift over an empirical permutation baseline. Across diverse foundation models, a simple pipeline, frozen Whisper encoder features, time-frequency pooling, and label-free PCA, yields strong zero-shot performance. However, VocSim also uncovers a consistent generalization gap. On blind, low-resource speech, local retrieval drops sharply. While performance remains statistically distinguishable from chance, the absolute geometric structure collapses, indicating a failure to generalize to unseen phonotactics. As external validation, our top embeddings predict avian perceptual similarity, improve bioacoustic classification, and achieve state-of-the-art results on the HEAR benchmark. We posit that the intrinsic geometric quality measured here proxies utility in unlisted downstream applications. We release data, code, and a public leaderboard to standardize the evaluation of intrinsic audio geometry.

Robust Speech Activity Detection in the Presence of Singing Voice

Speech Activity Detection (SAD) systems often misclassify singing as speech, leading to degraded performance in applications such as dialogue enhancement and automatic speech recognition. We introduce Singing-Robust Speech Activity Detection ( SR-SAD ), a neural network designed to robustly detect speech in the presence of singing. Our key contributions are: i) a training strategy using controlled ratios of speech and singing samples to improve discrimination, ii) a computationally efficient model that maintains robust performance while reducing inference runtime, and iii) a new evaluation metric tailored to assess SAD robustness in mixed speech-singing scenarios. Experiments on a challenging dataset spanning multiple musical genres show that SR-SAD maintains high speech detection accuracy (AUC = 0.919) while rejecting singing. By explicitly learning to distinguish between speech and singing, SR-SAD enables more reliable SAD in mixed speech-singing scenarios.

Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection

Hate speech spreads widely online, harming individuals and communities, making automatic detection essential for large-scale moderation, yet detecting it remains difficult. Part of the challenge lies in subjectivity: what one person flags as hate speech, another may see as benign. Traditional annotation agreement metrics, such as Cohen's $κ$, oversimplify this disagreement, treating it as an error rather than meaningful diversity. Meanwhile, Large Language Models (LLMs) promise scalable annotation, but prior studies demonstrate that they cannot fully replace human judgement, especially in subjective tasks. In this work, we reexamine LLM reliability using a subjectivity-aware framework, cross-Rater Reliability (xRR), revealing that even under fairer lens, LLMs still diverge from humans. Yet this limitation opens an opportunity: we find that LLM-generated annotations can reliably reflect performance trends across classification models, correlating with human evaluations. We test this by examining whether LLM-generated annotations preserve the relative ordering of model performance derived from human evaluation (i.e. whether models ranked as more reliable by human annotators preserve the same order when evaluated with LLM-generated labels). Our results show that, although LLMs differ from humans at the instance level, they reproduce similar ranking and classification patterns, suggesting their potential as proxy evaluators. While not a substitute for human annotators, they might serve as a scalable proxy for evaluation in subjective NLP tasks.

A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques

Body and face motion play an integral role in communication. They convey crucial information on the participants. Advances in generative modeling and multi-modal learning have enabled motion generation from signals such as speech, conversational context and visual cues. However, generating expressive and coherent face and body dynamics remains challenging due to the complex interplay of verbal / non-verbal cues and individual personality traits. This survey reviews body and face motion generation, covering core concepts, representations techniques, generative approaches, datasets and evaluation metrics. We highlight future directions to enhance the realism, coherence and expressiveness of avatars in dyadic settings. To the best of our knowledge, this work is the first comprehensive review to cover both body and face motion. Detailed resources are listed on https://lownish23csz0010.github.io/mogen/.

SpeechQualityLLM: LLM-Based Multimodal Assessment of Speech Quality

Objective speech quality assessment is central to telephony, VoIP, and streaming systems, where large volumes of degraded audio must be monitored and optimized at scale. Classical metrics such as PESQ and POLQA approximate human mean opinion scores (MOS) but require carefully controlled conditions and expensive listening tests, while learning-based models such as NISQA regress MOS and multiple perceptual dimensions from waveforms or spectrograms, achieving high correlation with subjective ratings yet remaining rigid: they do not support interactive, natural-language queries and do not natively provide textual rationales. In this work, we introduce SpeechQualityLLM, a multimodal speech quality question-answering (QA) system that couples an audio encoder with a language model and is trained on the NISQA corpus using template-based question-answer pairs covering overall MOS and four perceptual dimensions (noisiness, coloration, discontinuity, and loudness) in both single-ended (degraded only) and double-ended (degraded plus clean reference) setups. Instead of directly regressing scores, our system is supervised to generate textual answers from which numeric predictions are parsed and evaluated with standard regression and ranking metrics; on held-out NISQA clips, the double-ended model attains a MOS mean absolute error (MAE) of 0.41 with Pearson correlation of 0.86, with competitive performance on dimension-wise tasks. Beyond these quantitative gains, it offers a flexible natural-language interface in which the language model acts as an audio quality expert: practitioners can query arbitrary aspects of degradations, prompt the model to emulate different listener profiles to capture human variability and produce diverse but plausible judgments rather than a single deterministic score, and thereby reduce reliance on large-scale crowdsourced tests and their monetary cost.

BUT Systems for Environmental Sound Deepfake Detection in the ESDD 2026 Challenge

This paper describes the BUT submission to the ESDD 2026 Challenge, specifically focusing on Track 1: Environmental Sound Deepfake Detection with Unseen Generators. To address the critical challenge of generalizing to audio generated by unseen synthesis algorithms, we propose a robust ensemble framework leveraging diverse Self-Supervised Learning (SSL) models. We conduct a comprehensive analysis of general audio SSL models (including BEATs, EAT, and Dasheng) and speech-specific SSLs. These front-ends are coupled with a lightweight Multi-Head Factorized Attention (MHFA) back-end to capture discriminative representations. Furthermore, we introduce a feature domain augmentation strategy based on distribution uncertainty modeling to enhance model robustness against unseen spectral distortions. All models are trained exclusively on the official EnvSDD data, without using any external resources. Experimental results demonstrate the effectiveness of our approach: our best single system achieved Equal Error Rates (EER) of 0.00\%, 4.60\%, and 4.80\% on the Development, Progress (Track 1), and Final Evaluation sets, respectively. The fusion system further improved generalization, yielding EERs of 0.00\%, 3.52\%, and 4.38\% across the same partitions.